{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/within-eps","entry":"within_eps","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":7,"n_papers_ran":4,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":3,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":1},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2505.21413","paper":null,"title":"arXiv:2505.21413","date":null,"month_inferred_from_arxiv_id":"2025-05","title_source":null,"repo":"xxxiaol/RefTool","path":"code/inference/evaluation_utils.py","file_url":"https://github.com/xxxiaol/RefTool/blob/HEAD/code/inference/evaluation_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"98b05a45dfc53b99","mcp_get_code":{"code_sha256":"98b05a45dfc53b99"}},{"arxiv_id":"2412.01981","paper":"/paper/free-process-rewards-without-process-labels","title":"Free Process Rewards without Process Labels","date":"2024-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lifan-yuan/implicitprm","path":"eval/math_utils/eval_theoremqa.py","file_url":"https://github.com/lifan-yuan/implicitprm/blob/HEAD/eval/math_utils/eval_theoremqa.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"98b05a45dfc53b99","mcp_get_code":{"code_sha256":"98b05a45dfc53b99"}},{"arxiv_id":"2409.12147","paper":"/paper/magicore-multi-agent-iterative-coarse-to-fine","title":"MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning","date":"2024-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dinobby/magicore","path":"math_utils.py","file_url":"https://github.com/dinobby/magicore/blob/HEAD/math_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e8f6bab9810c154d","mcp_get_code":{"code_sha256":"e8f6bab9810c154d"}},{"arxiv_id":"2311.09805","paper":"/paper/docmath-eval-evaluating-numerical-reasoning","title":"DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yale-nlp/docmath-eval","path":"utils/evaluation_utils.py","file_url":"https://github.com/yale-nlp/docmath-eval/blob/HEAD/utils/evaluation_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05e59123f91ef53c","mcp_get_code":{"code_sha256":"05e59123f91ef53c"}},{"arxiv_id":"2311.09797","paper":"/paper/knowledgemath-knowledge-intensive-math-word","title":"FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yale-nlp/knowledgemath","path":"utils/evaluation_utils.py","file_url":"https://github.com/yale-nlp/knowledgemath/blob/HEAD/utils/evaluation_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05e59123f91ef53c","mcp_get_code":{"code_sha256":"05e59123f91ef53c"}},{"arxiv_id":"2025.findings-acl.605","paper":null,"title":"arXiv:2025.findings-acl.605","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ytyz1307zzh/RefAug","path":"src/evaluate/eval_mathinstruct.py","file_url":"https://github.com/ytyz1307zzh/RefAug/blob/HEAD/src/evaluate/eval_mathinstruct.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"98b05a45dfc53b99","mcp_get_code":{"code_sha256":"98b05a45dfc53b99"}},{"arxiv_id":"2025.emnlp-main.1660","paper":null,"title":"arXiv:2025.emnlp-main.1660","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"dinobby/MAgICoRe","path":"math_utils.py","file_url":"https://github.com/dinobby/MAgICoRe/blob/HEAD/math_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e8f6bab9810c154d","mcp_get_code":{"code_sha256":"e8f6bab9810c154d"}}]}